[Feature] Update New SegFormer models (open-mmlab#1705)

AetrexTechnology · Jun 25, 2022 · 06d40a1 · 06d40a1
1 parent 1a18f1f
commit 06d40a1
Show file tree

Hide file tree

Showing 15 changed files with 101 additions and 66 deletions.
diff --git a/configs/segformer/README.md b/configs/segformer/README.md
diff --git a/configs/segformer/segformer.yml b/configs/segformer/segformer.yml
@@ -22,7 +22,7 @@ Models:
     crop size: (512,512)
     lr schd: 160000
     inference time (ms/im):
-    - value: 19.49
+    - value: 26.2
       hardware: V100
       backend: PyTorch
       batch size: 1
@@ -33,18 +33,18 @@ Models:
   - Task: Semantic Segmentation
     Dataset: ADE20K
     Metrics:
-      mIoU: 37.41
-      mIoU(ms+flip): 38.34
+      mIoU: 37.85
+      mIoU(ms+flip): 38.97
   Config: configs/segformer/segformer_mit-b0_512x512_160k_ade20k.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20220617_162207-c00b9603.pth
 - Name: segformer_mit-b1_512x512_160k_ade20k
   In Collection: Segformer
   Metadata:
     backbone: MIT-B1
     crop size: (512,512)
     lr schd: 160000
     inference time (ms/im):
-    - value: 20.98
+    - value: 26.46
       hardware: V100
       backend: PyTorch
       batch size: 1
@@ -55,18 +55,18 @@ Models:
   - Task: Semantic Segmentation
     Dataset: ADE20K
     Metrics:
-      mIoU: 40.97
-      mIoU(ms+flip): 42.54
+      mIoU: 42.13
+      mIoU(ms+flip): 43.74
   Config: configs/segformer/segformer_mit-b1_512x512_160k_ade20k.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20220620_112037-c3f39e00.pth
 - Name: segformer_mit-b2_512x512_160k_ade20k
   In Collection: Segformer
   Metadata:
     backbone: MIT-B2
     crop size: (512,512)
     lr schd: 160000
     inference time (ms/im):
-    - value: 32.38
+    - value: 37.31
       hardware: V100
       backend: PyTorch
       batch size: 1
@@ -77,18 +77,18 @@ Models:
   - Task: Semantic Segmentation
     Dataset: ADE20K
     Metrics:
-      mIoU: 45.58
-      mIoU(ms+flip): 47.03
+      mIoU: 46.8
+      mIoU(ms+flip): 48.12
   Config: configs/segformer/segformer_mit-b2_512x512_160k_ade20k.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20220620_114047-64e4feca.pth
 - Name: segformer_mit-b3_512x512_160k_ade20k
   In Collection: Segformer
   Metadata:
     backbone: MIT-B3
     crop size: (512,512)
     lr schd: 160000
     inference time (ms/im):
-    - value: 45.23
+    - value: 52.11
       hardware: V100
       backend: PyTorch
       batch size: 1
@@ -99,18 +99,18 @@ Models:
   - Task: Semantic Segmentation
     Dataset: ADE20K
     Metrics:
-      mIoU: 47.82
-      mIoU(ms+flip): 48.81
+      mIoU: 48.25
+      mIoU(ms+flip): 49.58
   Config: configs/segformer/segformer_mit-b3_512x512_160k_ade20k.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20220617_162254-3a4b7363.pth
 - Name: segformer_mit-b4_512x512_160k_ade20k
   In Collection: Segformer
   Metadata:
     backbone: MIT-B4
     crop size: (512,512)
     lr schd: 160000
     inference time (ms/im):
-    - value: 64.72
+    - value: 68.78
       hardware: V100
       backend: PyTorch
       batch size: 1
@@ -121,10 +121,10 @@ Models:
   - Task: Semantic Segmentation
     Dataset: ADE20K
     Metrics:
-      mIoU: 48.46
-      mIoU(ms+flip): 49.76
+      mIoU: 49.09
+      mIoU(ms+flip): 50.72
   Config: configs/segformer/segformer_mit-b4_512x512_160k_ade20k.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20220620_112216-4fa4f58f.pth
 - Name: segformer_mit-b5_512x512_160k_ade20k
   In Collection: Segformer
   Metadata:
@@ -154,7 +154,7 @@ Models:
     crop size: (640,640)
     lr schd: 160000
     inference time (ms/im):
-    - value: 88.5
+    - value: 94.34
       hardware: V100
       backend: PyTorch
       batch size: 1
@@ -165,10 +165,10 @@ Models:
   - Task: Semantic Segmentation
     Dataset: ADE20K
     Metrics:
-      mIoU: 49.62
-      mIoU(ms+flip): 50.36
+      mIoU: 50.19
+      mIoU(ms+flip): 51.41
   Config: configs/segformer/segformer_mit-b5_640x640_160k_ade20k.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20220617_203542-940a6bd8.pth
 - Name: segformer_mit-b0_8x1_1024x1024_160k_cityscapes
   In Collection: Segformer
   Metadata:

diff --git a/configs/segformer/segformer_mit-b0_512x512_160k_ade20k.py b/configs/segformer/segformer_mit-b0_512x512_160k_ade20k.py
@@ -3,8 +3,9 @@
     '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
 ]
 
-model = dict(
-    pretrained='pretrain/mit_b0.pth', decode_head=dict(num_classes=150))
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b0_20220624-7e0fe6dd.pth'  # noqa
+
+model = dict(pretrained=checkpoint, decode_head=dict(num_classes=150))
 
 # optimizer
 optimizer = dict(

diff --git a/configs/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py b/configs/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py
@@ -4,9 +4,10 @@
     '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
 ]
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b0_20220624-7e0fe6dd.pth'  # noqa
+
 model = dict(
-    backbone=dict(
-        init_cfg=dict(type='Pretrained', checkpoint='pretrain/mit_b0.pth')),
+    backbone=dict(init_cfg=dict(type='Pretrained', checkpoint=checkpoint)),
     test_cfg=dict(mode='slide', crop_size=(1024, 1024), stride=(768, 768)))
 
 # optimizer

diff --git a/configs/segformer/segformer_mit-b1_512x512_160k_ade20k.py b/configs/segformer/segformer_mit-b1_512x512_160k_ade20k.py
@@ -1,8 +1,10 @@
 _base_ = ['./segformer_mit-b0_512x512_160k_ade20k.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b1_20220624-02e5a6a1.pth'  # noqa
+
 # model settings
 model = dict(
-    pretrained='pretrain/mit_b1.pth',
+    pretrained=checkpoint,
     backbone=dict(
         embed_dims=64, num_heads=[1, 2, 5, 8], num_layers=[2, 2, 2, 2]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes.py b/configs/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes.py
@@ -1,7 +1,8 @@
 _base_ = ['./segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b1_20220624-02e5a6a1.pth'  # noqa
 model = dict(
     backbone=dict(
-        init_cfg=dict(type='Pretrained', checkpoint='pretrain/mit_b1.pth'),
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint),
         embed_dims=64),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b2_512x512_160k_ade20k.py b/configs/segformer/segformer_mit-b2_512x512_160k_ade20k.py
@@ -1,8 +1,10 @@
 _base_ = ['./segformer_mit-b0_512x512_160k_ade20k.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b2_20220624-66e8bf70.pth'  # noqa
+
 # model settings
 model = dict(
-    pretrained='pretrain/mit_b2.pth',
+    pretrained=checkpoint,
     backbone=dict(
         embed_dims=64, num_heads=[1, 2, 5, 8], num_layers=[3, 4, 6, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes.py b/configs/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes.py
@@ -1,8 +1,9 @@
 _base_ = ['./segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b2_20220624-66e8bf70.pth'  # noqa
 model = dict(
     backbone=dict(
-        init_cfg=dict(type='Pretrained', checkpoint='pretrain/mit_b2.pth'),
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint),
         embed_dims=64,
         num_layers=[3, 4, 6, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b3_512x512_160k_ade20k.py b/configs/segformer/segformer_mit-b3_512x512_160k_ade20k.py
@@ -1,8 +1,10 @@
 _base_ = ['./segformer_mit-b0_512x512_160k_ade20k.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b3_20220624-13b1141c.pth'  # noqa
+
 # model settings
 model = dict(
-    pretrained='pretrain/mit_b3.pth',
+    pretrained=checkpoint,
     backbone=dict(
         embed_dims=64, num_heads=[1, 2, 5, 8], num_layers=[3, 4, 18, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes.py b/configs/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes.py
@@ -1,8 +1,9 @@
 _base_ = ['./segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b3_20220624-13b1141c.pth'  # noqa
 model = dict(
     backbone=dict(
-        init_cfg=dict(type='Pretrained', checkpoint='pretrain/mit_b3.pth'),
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint),
         embed_dims=64,
         num_layers=[3, 4, 18, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b4_512x512_160k_ade20k.py b/configs/segformer/segformer_mit-b4_512x512_160k_ade20k.py
@@ -1,8 +1,10 @@
 _base_ = ['./segformer_mit-b0_512x512_160k_ade20k.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b4_20220624-d588d980.pth'  # noqa
+
 # model settings
 model = dict(
-    pretrained='pretrain/mit_b4.pth',
+    pretrained=checkpoint,
     backbone=dict(
         embed_dims=64, num_heads=[1, 2, 5, 8], num_layers=[3, 8, 27, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes.py b/configs/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes.py
@@ -1,8 +1,9 @@
 _base_ = ['./segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b4_20220624-d588d980.pth'  # noqa
 model = dict(
     backbone=dict(
-        init_cfg=dict(type='Pretrained', checkpoint='pretrain/mit_b4.pth'),
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint),
         embed_dims=64,
         num_layers=[3, 8, 27, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b5_512x512_160k_ade20k.py b/configs/segformer/segformer_mit-b5_512x512_160k_ade20k.py
@@ -1,8 +1,10 @@
 _base_ = ['./segformer_mit-b0_512x512_160k_ade20k.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b5_20220624-658746d9.pthh'  # noqa
+
 # model settings
 model = dict(
-    pretrained='pretrain/mit_b5.pth',
+    pretrained=checkpoint,
     backbone=dict(
         embed_dims=64, num_heads=[1, 2, 5, 8], num_layers=[3, 6, 40, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b5_640x640_160k_ade20k.py b/configs/segformer/segformer_mit-b5_640x640_160k_ade20k.py
@@ -37,8 +37,9 @@
     test=dict(pipeline=test_pipeline))
 
 # model settings
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b5_20220624-658746d9.pthh'  # noqa
 model = dict(
-    pretrained='pretrain/mit_b5.pth',
+    pretrained=checkpoint,
     backbone=dict(
         embed_dims=64, num_heads=[1, 2, 5, 8], num_layers=[3, 6, 40, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))
diff --git a/configs/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes.py b/configs/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes.py
@@ -1,8 +1,9 @@
 _base_ = ['./segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py']
 
+checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segformer/mit_b5_20220624-658746d9.pthh'  # noqa
 model = dict(
     backbone=dict(
-        init_cfg=dict(type='Pretrained', checkpoint='pretrain/mit_b5.pth'),
+        init_cfg=dict(type='Pretrained', checkpoint=checkpoint),
         embed_dims=64,
         num_layers=[3, 6, 40, 3]),
     decode_head=dict(in_channels=[64, 128, 320, 512]))